Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.18599 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910846778605568 |
|---|---|
| author | Rostami, Mohammad Faysal, Atik Wang, Huaxia Sahoo, Avimanyu |
| author_facet | Rostami, Mohammad Faysal, Atik Wang, Huaxia Sahoo, Avimanyu |
| contents | Overfitting is a significant challenge in Few-Shot Learning (FSL), where models trained on small, variable datasets tend to memorize rather than generalize to unseen tasks. Regularization is crucial in FSL to prevent overfitting and enhance generalization performance. To address this issue, we introduce Meta-Task, a novel, method-agnostic framework that leverages both labeled and unlabeled data to enhance generalization through auxiliary tasks for regularization. Specifically, Meta-Task introduces a Task-Decoder, which is a simple example of the broader framework that refines hidden representations by reconstructing input images from embeddings, effectively mitigating overfitting.
Our framework's method-agnostic design ensures its broad applicability across various FSL settings. We validate Meta-Task's effectiveness on standard benchmarks, including Mini-ImageNet, Tiered-ImageNet, and FC100, where it consistently improves existing state-of-the-art meta-learning techniques, demonstrating superior performance, faster convergence, reduced generalization error, and lower variance-all without extensive hyperparameter tuning. These results underline Meta-Task's practical applicability and efficiency in real-world, resource-constrained scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18599 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learning Rostami, Mohammad Faysal, Atik Wang, Huaxia Sahoo, Avimanyu Machine Learning Artificial Intelligence Overfitting is a significant challenge in Few-Shot Learning (FSL), where models trained on small, variable datasets tend to memorize rather than generalize to unseen tasks. Regularization is crucial in FSL to prevent overfitting and enhance generalization performance. To address this issue, we introduce Meta-Task, a novel, method-agnostic framework that leverages both labeled and unlabeled data to enhance generalization through auxiliary tasks for regularization. Specifically, Meta-Task introduces a Task-Decoder, which is a simple example of the broader framework that refines hidden representations by reconstructing input images from embeddings, effectively mitigating overfitting. Our framework's method-agnostic design ensures its broad applicability across various FSL settings. We validate Meta-Task's effectiveness on standard benchmarks, including Mini-ImageNet, Tiered-ImageNet, and FC100, where it consistently improves existing state-of-the-art meta-learning techniques, demonstrating superior performance, faster convergence, reduced generalization error, and lower variance-all without extensive hyperparameter tuning. These results underline Meta-Task's practical applicability and efficiency in real-world, resource-constrained scenarios. |
| title | Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.18599 |